antlr
Class PythonCodeGenerator

java.lang.Object
  extended byantlr.CodeGenerator
      extended byantlr.PythonCodeGenerator

public class PythonCodeGenerator
extends CodeGenerator

Generate MyParser.java, MyLexer.java and MyParserTokenTypes.java


Field Summary
(package private)  int astVarNumber
           
static int caseSizeThreshold
           
(package private)  String commonExtraArgs
           
(package private)  String commonExtraParams
           
(package private)  String commonLocalVars
           
(package private)  String currentASTResult
          Tracks the rule or labeled subrule being generated.
(package private)  RuleBlock currentRule
          Tracks the rule being generated.
(package private)  Hashtable declaredASTVariables
          Used to keep track of which AST variables have been defined in a rule (except for the #rule_name and #rule_name_in var's
(package private)  String exceptionThrown
           
protected  boolean genAST
           
static String initHeaderAction
           
(package private)  String labeledElementASTType
           
(package private)  String labeledElementInit
           
(package private)  String labeledElementType
           
(package private)  String lexerClassName
           
(package private)  String lt1Value
           
static String mainHeaderAction
           
protected static String NONUNIQUE
          Special value used to mark duplicate in treeVariableMap
(package private)  String parserClassName
           
protected  boolean saveText
           
protected  int syntacticPredLevel
           
(package private)  String throwNoViable
           
(package private)  Hashtable treeVariableMap
          Mapping between the ids used in the current alt, and the names of variables used to represent their AST values.
(package private)  String treeWalkerClassName
           
 
Fields inherited from class antlr.CodeGenerator
analyzer, antlrTool, behavior, BITSET_OPTIMIZE_INIT_THRESHOLD, bitsetsUsed, bitsetTestThreshold, charFormatter, currentOutput, DEBUG_CODE_GENERATOR, DEFAULT_BITSET_TEST_THRESHOLD, DEFAULT_MAKE_SWITCH_THRESHOLD, grammar, makeSwitchThreshold, tabs, TokenTypesFileExt, TokenTypesFileSuffix
 
Constructor Summary
PythonCodeGenerator()
           
 
Method Summary
protected  void _printAction(String s)
          Print an action without leading tabs, attempting to preserve the current indentation level for multi-line actions Ignored if string is null.
protected  void _printJavadoc(String s)
           
protected  int addSemPred(String predicate)
          Adds a semantic predicate string to the sem pred vector These strings will be used to build an array of sem pred names when building a debugging parser.
protected  void checkCurrentOutputStream()
           
 void exitIfError()
           
protected  String extractIdOfAction(String s, int line, int column)
          Get the identifier portion of an argument-action.
protected  String extractTypeOfAction(String s, int line, int column)
          Get the type portion of an argument-action.
protected  void flushTokens()
           
 void gen()
          Generate the parser, lexer, treeparser, and token types in Java
 void gen(ActionElement action)
          Generate code for the given grammar element.
 void gen(AlternativeBlock blk)
          Generate code for the given grammar element.
 void gen(BlockEndElement end)
          Generate code for the given grammar element.
 void gen(CharLiteralElement atom)
          Generate code for the given grammar element.
 void gen(CharRangeElement r)
          Generate code for the given grammar element.
 void gen(LexerGrammar g)
          Generate the lexer Java file
 void gen(OneOrMoreBlock blk)
          Generate code for the given grammar element.
 void gen(ParserGrammar g)
          Generate the parser Java file
 void gen(RuleRefElement rr)
          Generate code for the given grammar element.
 void gen(StringLiteralElement atom)
          Generate code for the given grammar element.
 void gen(TokenRangeElement r)
          Generate code for the given grammar element.
 void gen(TokenRefElement atom)
          Generate code for the given grammar element.
 void gen(TreeElement t)
          Generate code for the given grammar element.
 void gen(TreeWalkerGrammar g)
          Generate the tree-parser Java file
 void gen(WildcardElement wc)
          Generate code for the given grammar element.
 void gen(ZeroOrMoreBlock blk)
          Generate code for the given grammar element.
protected  void genAlt(Alternative alt, AlternativeBlock blk)
          Generate an alternative.
protected  void genASTDeclaration(AlternativeElement el)
           
protected  void genASTDeclaration(AlternativeElement el, String node_type)
           
protected  void genASTDeclaration(AlternativeElement el, String var_name, String node_type)
           
protected  void genBitsets(Vector bitsetList, int maxVocabulary)
          Generate all the bitsets to be used in the parser or lexer Generate the raw bitset data like "long _tokenSet1_data[] = {...}" and the BitSet object declarations like "BitSet _tokenSet1 = new BitSet(_tokenSet1_data)" Note that most languages do not support object initialization inside a class definition, so other code-generators may have to separate the bitset declarations from the initializations (e.g., put the initializations in the generated constructor instead).
protected  void genBlockInitAction(AlternativeBlock blk)
          Generate the init action for a block, which may be a RuleBlock or a plain AlternativeBLock.
protected  void genBlockPreamble(AlternativeBlock blk)
          Generate the header for a block, which may be a RuleBlock or a plain AlternativeBLock.
protected  void genCases(BitSet p)
          Generate a series of case statements that implement a BitSet test.
 PythonBlockFinishingInfo genCommonBlock(AlternativeBlock blk, boolean noTestForSingle)
          Generate common code for a block of alternatives; return a postscript that needs to be generated at the end of the block.
protected  void genHeader()
          Generate a header that is common to all Python files
protected  void genHeaderInit(Grammar grammar)
           
protected  void genHeaderMain(Grammar grammar)
           
protected  void genJavadocComment(Grammar g)
           
protected  void genJavadocComment(RuleSymbol g)
           
protected  void genLexerTest()
          Generate an automated test for Python CharScanner (sub)classes.
protected  void genMatch(BitSet b)
           
protected  void genMatch(GrammarAtom atom)
           
protected  void genMatchUsingAtomText(GrammarAtom atom)
           
protected  void genMatchUsingAtomTokenType(GrammarAtom atom)
           
 void genNextToken()
          Generate the nextToken() rule.
 void genRule(RuleSymbol s, boolean startSymbol, int ruleNum)
          Gen a named rule block.
protected  void genSemPred(String pred, int line)
           
protected  void genSemPredMap()
          Write an array of Strings which are the semantic predicate expressions.
protected  void genSynPred(SynPredBlock blk, String lookaheadExpr)
           
protected  void genTokenASTNodeMap()
          Create and set Integer token type objects that map to Java Class objects (which AST node to create).
 void genTokenStrings()
          Generate a static array containing the names of the tokens, indexed by the token type values.
protected  void genTokenTypes(TokenManager tm)
          Generate the token types Java file
 String getASTCreateString(GrammarAtom atom, String astCtorArgs)
          Get a string for an expression to generate creating of an AST node
 String getASTCreateString(String astCtorArgs)
          Get a string for an expression to generate creating of an AST node.
 String getASTCreateString(Vector v)
          Get a string for an expression to generate creation of an AST subtree.
protected  String getLookaheadTestExpression(Alternative alt, int maxDepth)
          Generate a lookahead test expression for an alternate.
protected  String getLookaheadTestExpression(Lookahead[] look, int k)
           
protected  String getLookaheadTestTerm(int k, BitSet p)
          Generate a depth==1 lookahead test expression given the BitSet.
 String getRangeExpression(int k, int[] elems)
          Return an expression for testing a contiguous renage of elements
(package private) static boolean isEmpty(String s)
           
protected  boolean isspace(char c)
           
protected  boolean lookaheadIsEmpty(Alternative alt, int maxDepth)
          Is the lookahead for this alt empty?
 String mapTreeId(String idParam, ActionTransInfo transInfo)
          Map an identifier to it's corresponding tree-node variable.
protected  void od(String s, int i, int end, String msg)
           
protected  void printAction(String s)
          Print an action with leading tabs, attempting to preserve the current indentation level for multi-line actions Ignored if string is null.
protected  void printActionCode(String actionStr, int line)
           
protected  void printGrammarAction(Grammar grammar)
           
protected  void printMainFunc(String s)
           
protected  void printTabs()
          Create a Java code-generator using the given Grammar.
protected  String processActionCode(String actionStr, int line)
           
protected  String processActionForSpecialSymbols(String actionStr, int line, RuleBlock currentRule, ActionTransInfo tInfo)
          Lexically process $var and tree-specifiers in the action.
 void setupOutput(String className)
          This method exists so a subclass, namely VAJCodeGenerator, can open the file in its own evil way.
(package private)  String toString(boolean v)
           
 
Methods inherited from class antlr.CodeGenerator
_print, _println, decodeLexerRuleName, elementsAreRange, encodeLexerRuleName, extractIdOfAction, extractTypeOfAction, genTokenInterchange, getBitsetName, getFIRSTBitSet, getFOLLOWBitSet, markBitsetForGen, print, println, processStringForASTConstructor, removeAssignmentFromDeclaration, reverseLexerRuleName, setAnalyzer, setBehavior, setGrammar, setTool
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Field Detail

syntacticPredLevel

protected int syntacticPredLevel

genAST

protected boolean genAST

saveText

protected boolean saveText

labeledElementType

String labeledElementType

labeledElementASTType

String labeledElementASTType

labeledElementInit

String labeledElementInit

commonExtraArgs

String commonExtraArgs

commonExtraParams

String commonExtraParams

commonLocalVars

String commonLocalVars

lt1Value

String lt1Value

exceptionThrown

String exceptionThrown

throwNoViable

String throwNoViable

initHeaderAction

public static final String initHeaderAction
See Also:
Constant Field Values

mainHeaderAction

public static final String mainHeaderAction
See Also:
Constant Field Values

lexerClassName

String lexerClassName

parserClassName

String parserClassName

treeWalkerClassName

String treeWalkerClassName

currentRule

RuleBlock currentRule
Tracks the rule being generated. Used for mapTreeId


currentASTResult

String currentASTResult
Tracks the rule or labeled subrule being generated. Used for AST generation.


treeVariableMap

Hashtable treeVariableMap
Mapping between the ids used in the current alt, and the names of variables used to represent their AST values.


declaredASTVariables

Hashtable declaredASTVariables
Used to keep track of which AST variables have been defined in a rule (except for the #rule_name and #rule_name_in var's


astVarNumber

int astVarNumber

NONUNIQUE

protected static final String NONUNIQUE
Special value used to mark duplicate in treeVariableMap


caseSizeThreshold

public static final int caseSizeThreshold
See Also:
Constant Field Values
Constructor Detail

PythonCodeGenerator

public PythonCodeGenerator()
Method Detail

printTabs

protected void printTabs()
Create a Java code-generator using the given Grammar. The caller must still call setTool, setBehavior, and setAnalyzer before generating code.

Overrides:
printTabs in class CodeGenerator

addSemPred

protected int addSemPred(String predicate)
Adds a semantic predicate string to the sem pred vector These strings will be used to build an array of sem pred names when building a debugging parser. This method should only be called when the debug option is specified


exitIfError

public void exitIfError()

checkCurrentOutputStream

protected void checkCurrentOutputStream()

extractIdOfAction

protected String extractIdOfAction(String s,
                                   int line,
                                   int column)
Get the identifier portion of an argument-action. For Python the ID of an action is assumed to be everything before the assignment, as Python does not support a type.

Overrides:
extractIdOfAction in class CodeGenerator
Parameters:
s - The action text
line - Line used for error reporting.
column - Line used for error reporting.
Returns:
A string containing the text of the identifier

extractTypeOfAction

protected String extractTypeOfAction(String s,
                                     int line,
                                     int column)
Get the type portion of an argument-action. Python does not have a type declaration before an identifier, so we just return the empty string.

Overrides:
extractTypeOfAction in class CodeGenerator
Parameters:
s - The action text
line - Line used for error reporting.
Returns:
A string containing the text of the type

flushTokens

protected void flushTokens()

gen

public void gen()
Generate the parser, lexer, treeparser, and token types in Java

Specified by:
gen in class CodeGenerator

gen

public void gen(ActionElement action)
Generate code for the given grammar element.

Specified by:
gen in class CodeGenerator
Parameters:
action - The {...} action to generate

gen

public void gen(AlternativeBlock blk)
Generate code for the given grammar element.

Specified by:
gen in class CodeGenerator
Parameters:
blk - The "x|y|z|..." block to generate

gen

public void gen(BlockEndElement end)
Generate code for the given grammar element.

Specified by:
gen in class CodeGenerator
Parameters:
end - The block-end element to generate. Block-end elements are synthesized by the grammar parser to represent the end of a block.

gen

public void gen(CharLiteralElement atom)
Generate code for the given grammar element.

Specified by:
gen in class CodeGenerator
Parameters:
atom - The character literal reference to generate

toString

String toString(boolean v)

gen

public void gen(CharRangeElement r)
Generate code for the given grammar element.

Specified by:
gen in class CodeGenerator
Parameters:
r - The character-range reference to generate

gen

public void gen(LexerGrammar g)
         throws IOException
Generate the lexer Java file

Specified by:
gen in class CodeGenerator
Throws:
IOException

genHeaderMain

protected void genHeaderMain(Grammar grammar)

genHeaderInit

protected void genHeaderInit(Grammar grammar)

printMainFunc

protected void printMainFunc(String s)

gen

public void gen(OneOrMoreBlock blk)
Generate code for the given grammar element.

Specified by:
gen in class CodeGenerator
Parameters:
blk - The (...)+ block to generate

gen

public void gen(ParserGrammar g)
         throws IOException
Generate the parser Java file

Specified by:
gen in class CodeGenerator
Throws:
IOException

gen

public void gen(RuleRefElement rr)
Generate code for the given grammar element.

Specified by:
gen in class CodeGenerator
Parameters:
rr - The rule-reference to generate

gen

public void gen(StringLiteralElement atom)
Generate code for the given grammar element.

Specified by:
gen in class CodeGenerator
Parameters:
atom - The string-literal reference to generate

gen

public void gen(TokenRangeElement r)
Generate code for the given grammar element.

Specified by:
gen in class CodeGenerator
Parameters:
r - The token-range reference to generate

gen

public void gen(TokenRefElement atom)
Generate code for the given grammar element.

Specified by:
gen in class CodeGenerator
Parameters:
atom - The token-reference to generate

gen

public void gen(TreeElement t)
Description copied from class: CodeGenerator
Generate code for the given grammar element.

Specified by:
gen in class CodeGenerator

gen

public void gen(TreeWalkerGrammar g)
         throws IOException
Generate the tree-parser Java file

Specified by:
gen in class CodeGenerator
Throws:
IOException

gen

public void gen(WildcardElement wc)
Generate code for the given grammar element.

Specified by:
gen in class CodeGenerator
Parameters:
wc - The wildcard element to generate

gen

public void gen(ZeroOrMoreBlock blk)
Generate code for the given grammar element.

Specified by:
gen in class CodeGenerator
Parameters:
blk - The (...)* block to generate

genAlt

protected void genAlt(Alternative alt,
                      AlternativeBlock blk)
Generate an alternative.

Parameters:
alt - The alternative to generate
blk - The block to which the alternative belongs

genBitsets

protected void genBitsets(Vector bitsetList,
                          int maxVocabulary)
Generate all the bitsets to be used in the parser or lexer Generate the raw bitset data like "long _tokenSet1_data[] = {...}" and the BitSet object declarations like "BitSet _tokenSet1 = new BitSet(_tokenSet1_data)" Note that most languages do not support object initialization inside a class definition, so other code-generators may have to separate the bitset declarations from the initializations (e.g., put the initializations in the generated constructor instead).

Parameters:
bitsetList - The list of bitsets to generate.
maxVocabulary - Ensure that each generated bitset can contain at least this value.

genBlockInitAction

protected void genBlockInitAction(AlternativeBlock blk)
Generate the init action for a block, which may be a RuleBlock or a plain AlternativeBLock.


genBlockPreamble

protected void genBlockPreamble(AlternativeBlock blk)
Generate the header for a block, which may be a RuleBlock or a plain AlternativeBLock. This generates any variable declarations and syntactic-predicate-testing variables.


genCases

protected void genCases(BitSet p)
Generate a series of case statements that implement a BitSet test.

Parameters:
p - The Bitset for which cases are to be generated

genCommonBlock

public PythonBlockFinishingInfo genCommonBlock(AlternativeBlock blk,
                                               boolean noTestForSingle)
Generate common code for a block of alternatives; return a postscript that needs to be generated at the end of the block. Other routines may append else-clauses and such for error checking before the postfix is generated. If the grammar is a lexer, then generate alternatives in an order where alternatives requiring deeper lookahead are generated first, and EOF in the lookahead set reduces the depth of the lookahead. @param blk The block to generate @param noTestForSingle If true, then it does not generate a test for a single alternative.


genASTDeclaration

protected void genASTDeclaration(AlternativeElement el)

genASTDeclaration

protected void genASTDeclaration(AlternativeElement el,
                                 String node_type)

genASTDeclaration

protected void genASTDeclaration(AlternativeElement el,
                                 String var_name,
                                 String node_type)

genHeader

protected void genHeader()
Generate a header that is common to all Python files


genLexerTest

protected void genLexerTest()
Generate an automated test for Python CharScanner (sub)classes.


genMatch

protected void genMatch(BitSet b)

genMatch

protected void genMatch(GrammarAtom atom)

genMatchUsingAtomText

protected void genMatchUsingAtomText(GrammarAtom atom)

genMatchUsingAtomTokenType

protected void genMatchUsingAtomTokenType(GrammarAtom atom)

genNextToken

public void genNextToken()
Generate the nextToken() rule. nextToken() is a synthetic lexer rule that is the implicit OR of all user-defined lexer rules.


genRule

public void genRule(RuleSymbol s,
                    boolean startSymbol,
                    int ruleNum)
Gen a named rule block. ASTs are generated for each element of an alternative unless the rule or the alternative have a '!' modifier. If an alternative defeats the default tree construction, it must set _AST to the root of the returned AST. Each alternative that does automatic tree construction, builds up root and child list pointers in an ASTPair structure. A rule finishes by setting the returnAST variable from the ASTPair.

Parameters:
startSymbol - true if the rule is a start symbol (i.e., not referenced elsewhere)

genSemPred

protected void genSemPred(String pred,
                          int line)

genSemPredMap

protected void genSemPredMap()
Write an array of Strings which are the semantic predicate expressions. The debugger will reference them by number only


genSynPred

protected void genSynPred(SynPredBlock blk,
                          String lookaheadExpr)

genTokenStrings

public void genTokenStrings()
Generate a static array containing the names of the tokens, indexed by the token type values. This static array is used to format error messages so that the token identifers or literal strings are displayed instead of the token numbers. If a lexical rule has a paraphrase, use it rather than the token label.


genTokenASTNodeMap

protected void genTokenASTNodeMap()
Create and set Integer token type objects that map to Java Class objects (which AST node to create).


genTokenTypes

protected void genTokenTypes(TokenManager tm)
                      throws IOException
Generate the token types Java file

Throws:
IOException

getASTCreateString

public String getASTCreateString(Vector v)
Get a string for an expression to generate creation of an AST subtree.

Specified by:
getASTCreateString in class CodeGenerator
Parameters:
v - A Vector of String, where each element is an expression in the target language yielding an AST node.

getASTCreateString

public String getASTCreateString(GrammarAtom atom,
                                 String astCtorArgs)
Get a string for an expression to generate creating of an AST node

Specified by:
getASTCreateString in class CodeGenerator
Parameters:
atom - The grammar node for which you are creating the node
astCtorArgs - The text of the arguments to the AST construction

getASTCreateString

public String getASTCreateString(String astCtorArgs)
Get a string for an expression to generate creating of an AST node. Parse the first (possibly only) argument looking for the token type. If the token type is a valid token symbol, ask for it's AST node type and add to the end if only 2 arguments. The forms are #[T], #[T,"t"], and as of 2.7.2 #[T,"t",ASTclassname].


getLookaheadTestExpression

protected String getLookaheadTestExpression(Lookahead[] look,
                                            int k)

getLookaheadTestExpression

protected String getLookaheadTestExpression(Alternative alt,
                                            int maxDepth)
Generate a lookahead test expression for an alternate. This will be a series of tests joined by '&&' and enclosed by '()', the number of such tests being determined by the depth of the lookahead.


getLookaheadTestTerm

protected String getLookaheadTestTerm(int k,
                                      BitSet p)
Generate a depth==1 lookahead test expression given the BitSet. This may be one of: 1) a series of 'x==X||' tests 2) a range test using >= && <= where possible, 3) a bitset membership test for complex comparisons

Parameters:
k - The lookahead level
p - The lookahead set for level k

getRangeExpression

public String getRangeExpression(int k,
                                 int[] elems)
Return an expression for testing a contiguous renage of elements

Parameters:
k - The lookahead level
elems - The elements representing the set, usually from BitSet.toArray().
Returns:
String containing test expression.

lookaheadIsEmpty

protected boolean lookaheadIsEmpty(Alternative alt,
                                   int maxDepth)
Is the lookahead for this alt empty?


mapTreeId

public String mapTreeId(String idParam,
                        ActionTransInfo transInfo)
Map an identifier to it's corresponding tree-node variable. This is context-sensitive, depending on the rule and alternative being generated

Specified by:
mapTreeId in class CodeGenerator
Parameters:
idParam - The identifier name to map
Returns:
The mapped id (which may be the same as the input), or null if the mapping is invalid due to duplicates

processActionForSpecialSymbols

protected String processActionForSpecialSymbols(String actionStr,
                                                int line,
                                                RuleBlock currentRule,
                                                ActionTransInfo tInfo)
Lexically process $var and tree-specifiers in the action. This will replace #id and #(...) with the appropriate function calls and/or variables etc...

Specified by:
processActionForSpecialSymbols in class CodeGenerator

isEmpty

static boolean isEmpty(String s)

processActionCode

protected String processActionCode(String actionStr,
                                   int line)

printActionCode

protected void printActionCode(String actionStr,
                               int line)

setupOutput

public void setupOutput(String className)
                 throws IOException
This method exists so a subclass, namely VAJCodeGenerator, can open the file in its own evil way. JavaCodeGenerator simply opens a text file...

Throws:
IOException

isspace

protected boolean isspace(char c)

_printAction

protected void _printAction(String s)
Description copied from class: CodeGenerator
Print an action without leading tabs, attempting to preserve the current indentation level for multi-line actions Ignored if string is null.

Overrides:
_printAction in class CodeGenerator
Parameters:
s - The action string to output

od

protected void od(String s,
                  int i,
                  int end,
                  String msg)

printAction

protected void printAction(String s)
Description copied from class: CodeGenerator
Print an action with leading tabs, attempting to preserve the current indentation level for multi-line actions Ignored if string is null.

Overrides:
printAction in class CodeGenerator
Parameters:
s - The action string to output

printGrammarAction

protected void printGrammarAction(Grammar grammar)

_printJavadoc

protected void _printJavadoc(String s)

genJavadocComment

protected void genJavadocComment(Grammar g)

genJavadocComment

protected void genJavadocComment(RuleSymbol g)